From Diagnosis to Remission: Understanding Cancer Detection and Staging

Lung cancer remains a pervasive threat worldwide, necessitating early detection for effective treatment. Despite the promise of CT scan imaging, challenges persist in accurately identifying cancerous regions and determining cancer stage. To address this, computer-aided diagnosis employing image processing and machine learning, particularly SVM and CNN models, has gained traction. Our study evaluates these models, identifies limitations, and proposes enhancements. While CNN excels in detecting cancerous regions, achieving an impressive 94% accuracy, we augment its capabilities with advanced color-coding techniques to precisely identify tumor regions and classify cancer stages. Our approach aims to significantly improve diagnostic accuracy and clinical decision-making in lung cancer care.